Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 645 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.5337. Min Act: -0.1700

Data Index: 1422423 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.1274. Min Act: -0.1700

Data Index: 1477069 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.0961. Min Act: -0.1700

Data Index: 1539489 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.0648. Min Act: -0.1700

Data Index: 1497061 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.0336. Min Act: -0.1700

Data Index: 1513417 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.0336. Min Act: -0.1700

Data Index: 1602150 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 4.5337. Min Range: -4.5337

Max Act: 4.0023. Min Act: -0.1700

Data Index: 1600929 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9398. Min Act: -0.1700

Data Index: 1401094 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9398. Min Act: -0.1700

Data Index: 1501442 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9398. Min Act: -0.1700

Data Index: 1537546 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9398. Min Act: -0.1700

Data Index: 1587826 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1398385 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1620586 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1540437 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1620942 (Python Code)

Max Activating Token Index: 493

Text #15

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.9085. Min Act: -0.1700

Data Index: 1369629 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1617152 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1549636 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.8772. Min Act: -0.1700

Data Index: 1386159 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 4.5337. Min Range: -4.5337

Max Act: 3.8459. Min Act: -0.1700

Data Index: 1584866 (Python Code)

Max Activating Token Index: 1023